# coding: utf-8
from __future__ import unicode_literals
-import re
import itertools
+import re
from .common import (
InfoExtractor,
ExtractorError,
int_or_none,
unified_strdate,
+ update_url_query,
)
(?:(?:(?:www\.|m\.)?soundcloud\.com/
(?!stations/track)
(?P<uploader>[\w\d-]+)/
- (?!(?:tracks|sets(?:/.+?)?|reposts|likes|spotlight)/?(?:$|[?#]))
+ (?!(?:tracks|albums|sets(?:/.+?)?|reposts|likes|spotlight)/?(?:$|[?#]))
(?P<title>[\w\d-]+)/?
(?P<token>[^?]+?)?(?:[?].*)?$)
|(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+)
'license': 'cc-by-sa',
},
},
+ # private link, downloadable format
+ {
+ 'url': 'https://soundcloud.com/oriuplift/uponly-238-no-talking-wav/s-AyZUd',
+ 'md5': '64a60b16e617d41d0bef032b7f55441e',
+ 'info_dict': {
+ 'id': '340344461',
+ 'ext': 'wav',
+ 'title': 'Uplifting Only 238 [No Talking] (incl. Alex Feed Guestmix) (Aug 31, 2017) [wav]',
+ 'description': 'md5:fa20ee0fca76a3d6df8c7e57f3715366',
+ 'uploader': 'Ori Uplift Music',
+ 'upload_date': '20170831',
+ 'duration': 7449,
+ 'license': 'all-rights-reserved',
+ },
+ },
+ # no album art, use avatar pic for thumbnail
+ {
+ 'url': 'https://soundcloud.com/garyvee/sideways-prod-mad-real',
+ 'md5': '59c7872bc44e5d99b7211891664760c2',
+ 'info_dict': {
+ 'id': '309699954',
+ 'ext': 'mp3',
+ 'title': 'Sideways (Prod. Mad Real)',
+ 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
+ 'uploader': 'garyvee',
+ 'upload_date': '20170226',
+ 'duration': 207,
+ 'thumbnail': r're:https?://.*\.jpg',
+ 'license': 'all-rights-reserved',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ },
]
- _CLIENT_ID = '2t9loNQH90kzJcsFCODdigxfp325aq4z'
- _IPHONE_CLIENT_ID = '376f225bf427445fc4bfb6b99b72e0bf'
+ _CLIENT_ID = 'NmW1FlPaiL94ueEu7oziOWjYEzZzQDcK'
@staticmethod
def _extract_urls(webpage):
name = full_title or track_id
if quiet:
self.report_extraction(name)
- thumbnail = info.get('artwork_url')
+ thumbnail = info.get('artwork_url') or info.get('user', {}).get('avatar_url')
if isinstance(thumbnail, compat_str):
thumbnail = thumbnail.replace('-large', '-t500x500')
- ext = 'mp3'
result = {
'id': track_id,
'uploader': info.get('user', {}).get('username'),
'license': info.get('license'),
}
formats = []
+ query = {'client_id': self._CLIENT_ID}
+ if secret_token is not None:
+ query['secret_token'] = secret_token
if info.get('downloadable', False):
# We can build a direct link to the song
- format_url = (
- 'https://api.soundcloud.com/tracks/{0}/download?client_id={1}'.format(
- track_id, self._CLIENT_ID))
+ format_url = update_url_query(
+ 'https://api.soundcloud.com/tracks/%s/download' % track_id, query)
formats.append({
'format_id': 'download',
'ext': info.get('original_format', 'mp3'),
# We have to retrieve the url
format_dict = self._download_json(
'https://api.soundcloud.com/i1/tracks/%s/streams' % track_id,
- track_id, 'Downloading track url', query={
- 'client_id': self._CLIENT_ID,
- 'secret_token': secret_token,
- })
+ track_id, 'Downloading track url', query=query)
for key, stream_url in format_dict.items():
- abr = int_or_none(self._search_regex(
- r'_(\d+)_url', key, 'audio bitrate', default=None))
+ ext, abr = 'mp3', None
+ mobj = re.search(r'_([^_]+)_(\d+)_url', key)
+ if mobj:
+ ext, abr = mobj.groups()
+ abr = int(abr)
if key.startswith('http'):
stream_formats = [{
'format_id': key,
}]
elif key.startswith('hls'):
stream_formats = self._extract_m3u8_formats(
- stream_url, track_id, 'mp3', entry_protocol='m3u8_native',
+ stream_url, track_id, ext, entry_protocol='m3u8_native',
m3u8_id=key, fatal=False)
else:
continue
- for f in stream_formats:
- f['abr'] = abr
+ if abr:
+ for f in stream_formats:
+ f['abr'] = abr
formats.extend(stream_formats)
# cannot be always used, sometimes it can give an HTTP 404 error
formats.append({
'format_id': 'fallback',
- 'url': info['stream_url'] + '?client_id=' + self._CLIENT_ID,
- 'ext': ext,
+ 'url': update_url_query(info['stream_url'], query),
+ 'ext': 'mp3',
})
for f in formats:
class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE):
- _API_BASE = 'https://api.soundcloud.com'
_API_V2_BASE = 'https://api-v2.soundcloud.com'
def _extract_playlist(self, base_url, playlist_id, playlist_title):
next_href, playlist_id, 'Downloading track page %s' % (i + 1))
collection = response['collection']
- if not collection:
- break
+
+ if not isinstance(collection, list):
+ collection = []
+
+ # Empty collection may be returned, in this case we proceed
+ # straight to next_href
def resolve_permalink_url(candidates):
for cand in candidates:
(?:(?:www|m)\.)?soundcloud\.com/
(?P<user>[^/]+)
(?:/
- (?P<rsrc>tracks|sets|reposts|likes|spotlight)
+ (?P<rsrc>tracks|albums|sets|reposts|likes|spotlight)
)?
/?(?:[?#].*)?$
'''
IE_NAME = 'soundcloud:user'
_TESTS = [{
- 'url': 'https://soundcloud.com/the-akashic-chronicler',
+ 'url': 'https://soundcloud.com/soft-cell-official',
+ 'info_dict': {
+ 'id': '207965082',
+ 'title': 'Soft Cell (All)',
+ },
+ 'playlist_mincount': 28,
+ }, {
+ 'url': 'https://soundcloud.com/soft-cell-official/tracks',
'info_dict': {
- 'id': '114582580',
- 'title': 'The Akashic Chronicler (All)',
+ 'id': '207965082',
+ 'title': 'Soft Cell (Tracks)',
},
- 'playlist_mincount': 74,
+ 'playlist_mincount': 27,
}, {
- 'url': 'https://soundcloud.com/the-akashic-chronicler/tracks',
+ 'url': 'https://soundcloud.com/soft-cell-official/albums',
'info_dict': {
- 'id': '114582580',
- 'title': 'The Akashic Chronicler (Tracks)',
+ 'id': '207965082',
+ 'title': 'Soft Cell (Albums)',
},
- 'playlist_mincount': 37,
+ 'playlist_mincount': 1,
}, {
- 'url': 'https://soundcloud.com/the-akashic-chronicler/sets',
+ 'url': 'https://soundcloud.com/jcv246/sets',
'info_dict': {
- 'id': '114582580',
- 'title': 'The Akashic Chronicler (Playlists)',
+ 'id': '12982173',
+ 'title': 'Jordi / cv (Playlists)',
},
'playlist_mincount': 2,
}, {
- 'url': 'https://soundcloud.com/the-akashic-chronicler/reposts',
+ 'url': 'https://soundcloud.com/jcv246/reposts',
'info_dict': {
- 'id': '114582580',
- 'title': 'The Akashic Chronicler (Reposts)',
+ 'id': '12982173',
+ 'title': 'Jordi / cv (Reposts)',
},
- 'playlist_mincount': 7,
+ 'playlist_mincount': 6,
}, {
- 'url': 'https://soundcloud.com/the-akashic-chronicler/likes',
+ 'url': 'https://soundcloud.com/clalberg/likes',
'info_dict': {
- 'id': '114582580',
- 'title': 'The Akashic Chronicler (Likes)',
+ 'id': '11817582',
+ 'title': 'clalberg (Likes)',
},
- 'playlist_mincount': 321,
+ 'playlist_mincount': 5,
}, {
'url': 'https://soundcloud.com/grynpyret/spotlight',
'info_dict': {
}]
_BASE_URL_MAP = {
- 'all': '%s/profile/soundcloud:users:%%s' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
- 'tracks': '%s/users/%%s/tracks' % SoundcloudPagedPlaylistBaseIE._API_BASE,
+ 'all': '%s/stream/users/%%s' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
+ 'tracks': '%s/users/%%s/tracks' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
+ 'albums': '%s/users/%%s/albums' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
'sets': '%s/users/%%s/playlists' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
- 'reposts': '%s/profile/soundcloud:users:%%s/reposts' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
+ 'reposts': '%s/stream/users/%%s/reposts' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
'likes': '%s/users/%%s/likes' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
'spotlight': '%s/users/%%s/spotlight' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
}
_TITLE_MAP = {
'all': 'All',
'tracks': 'Tracks',
+ 'albums': 'Albums',
'sets': 'Playlists',
'reposts': 'Reposts',
'likes': 'Likes',
projects / youtube-dl / blobdiff